TEXTUAL KNOWLEDGE TRANSFER FOR IMPROVED SPEECH RECOGNITION AND UNDERSTANDING
Number of patents in Portfolio can not be more than 2000
United States of America
Stats
-
N/A
Issued Date -
Nov 7, 2024
app pub date -
May 2, 2023
filing date -
May 2, 2023
priority date (Note) -
Published
status (Latency Note)
Importance
Abstract
Systems, computer-implemented methods, and computer program products to facilitate fine-grained textual knowledge transfer to improve speech recognition and understanding are provided. According to an embodiment, a system can comprise a processor that executes components stored in memory. The computer executable components comprise deriving component that can derive one or more speech-based embeddings from an utterance via a speech encoder. The computer executable components can comprise a cross-attention component that can align, at a token level, one or more large language model (LLM) based sentence embeddings with the one or more speech-based embeddings. The computer executable components can comprise a loss component that can combine an alignment loss and an automatic speech recognition (ASR) loss.
First Claim
Family
International Classification(s)
Cited Art Landscape
Patent Citation Ranking
Recipient Email Address
Recipient Email Address
Comment
Recipient Email Address
Add to Portfolio(s)
To add this patent to one, or more, of your portfolios, simply click the add button.
This Patent is in these Portfolios:
Add to additional portfolios:
Last Refreshed On:
Changes done successfully